An Evidential Deep Network Based on Dempster-Shafer Theory for Large Dataset - Normandie Université Accéder directement au contenu
Chapitre D'ouvrage Année : 2023

An Evidential Deep Network Based on Dempster-Shafer Theory for Large Dataset

Résumé

We introduce a novel deep neural network architecture based on Dempster-Shafer theory capable of handling large image datasets with numerous classes, such as ImageNet. Our approach involves analyzing images through multiple experts, composed of convolutional deep neural networks that predict mass functions. These experts are then merged using Dempster's rule, thereby returning a set of potential classes by selecting the best expected utility based on the previously computed mass functions. Our innovative algorithm can identify the best set of classes among the 2 K possible sets for K classes while maintaining a complexity of O(K log(K)). To illustrate our approach, we apply it to an out-of-distribution example search problem, demonstrating its efficiency.
Fichier principal
Vignette du fichier
DSmT book 5 - Part 3 - Paper 39-v2.pdf (1.3 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04448387 , version 1 (09-02-2024)

Identifiants

  • HAL Id : hal-04448387 , version 1

Citer

Lucas Deregnaucourt, Alexis Lerchervy, Hind Laghmara, Samia Ainouz. An Evidential Deep Network Based on Dempster-Shafer Theory for Large Dataset. Florentin Smarandache; Jean Dezert; Albena Tchamova. Advances and Applications of DSmT for Information Fusion: Collected Works(Volume 5), pp.907-914, 2023. ⟨hal-04448387⟩
23 Consultations
9 Téléchargements

Partager

Gmail Facebook X LinkedIn More